Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    adjectives and descriptors that convey quality or value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Adjective followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    assessment of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apimachinery
    -0.60
     estekak
    -0.59
    __(/*!
    -0.59
     demurrer
    -0.57
     referenties
    -0.57
     hurricanes
    -0.55
    ContextHolder
    -0.54
     earthquakes
    -0.54
     crushes
    -0.53
    ofType
    -0.52
    POSITIVE LOGITS
     démarche
    0.64
     result
    0.63
     thing
    0.62
     يتيمه
    0.61
     sekali
    0.60
     way
    0.60
     cérami
    0.59
     vain
    0.57
     affair
    0.57
     intermédiaire
    0.57
    Act Density 0.231%

    No Known Activations